diff options
| author | Eric Dumazet <edumazet@google.com> | 2022-06-08 23:34:09 -0700 |
|---|---|---|
| committer | Jakub Kicinski <kuba@kernel.org> | 2022-06-10 16:21:26 -0700 |
| commit | 3cd3399dd7a84ada85cb839989cdf7310e302c7d (patch) | |
| tree | 8e815ea9747b1e3e1a7ca89414f4f9f35f3bf185 /include/net | |
| parent | 0defbb0af775ef037913786048d099bbe8b9a2c2 (diff) | |
| download | linux-3cd3399dd7a84ada85cb839989cdf7310e302c7d.tar.bz2 | |
net: implement per-cpu reserves for memory_allocated
We plan keeping sk->sk_forward_alloc as small as possible
in future patches.
This means we are going to call sk_memory_allocated_add()
and sk_memory_allocated_sub() more often.
Implement a per-cpu cache of +1/-1 MB, to reduce number
of changes to sk->sk_prot->memory_allocated, which
would otherwise be cause of false sharing.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'include/net')
| -rw-r--r-- | include/net/sock.h | 38 |
1 files changed, 29 insertions, 9 deletions
diff --git a/include/net/sock.h b/include/net/sock.h index 825f8cbf791f..59040fee74e7 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1398,21 +1398,47 @@ static inline bool sk_under_memory_pressure(const struct sock *sk) } static inline long +proto_memory_allocated(const struct proto *prot) +{ + return max(0L, atomic_long_read(prot->memory_allocated)); +} + +static inline long sk_memory_allocated(const struct sock *sk) { - return atomic_long_read(sk->sk_prot->memory_allocated); + return proto_memory_allocated(sk->sk_prot); } +/* 1 MB per cpu, in page units */ +#define SK_MEMORY_PCPU_RESERVE (1 << (20 - PAGE_SHIFT)) + static inline long sk_memory_allocated_add(struct sock *sk, int amt) { - return atomic_long_add_return(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_add_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve >= SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); + return sk_memory_allocated(sk); } static inline void sk_memory_allocated_sub(struct sock *sk, int amt) { - atomic_long_sub(amt, sk->sk_prot->memory_allocated); + int local_reserve; + + preempt_disable(); + local_reserve = __this_cpu_sub_return(*sk->sk_prot->per_cpu_fw_alloc, amt); + if (local_reserve <= -SK_MEMORY_PCPU_RESERVE) { + __this_cpu_sub(*sk->sk_prot->per_cpu_fw_alloc, local_reserve); + atomic_long_add(local_reserve, sk->sk_prot->memory_allocated); + } + preempt_enable(); } #define SK_ALLOC_PERCPU_COUNTER_BATCH 16 @@ -1441,12 +1467,6 @@ proto_sockets_allocated_sum_positive(struct proto *prot) return percpu_counter_sum_positive(prot->sockets_allocated); } -static inline long -proto_memory_allocated(struct proto *prot) -{ - return atomic_long_read(prot->memory_allocated); -} - static inline bool proto_memory_pressure(struct proto *prot) { |